search

dojo-sim / Dojo.jl

A differentiable physics engine for robotics
MIT License
309 stars 27 forks source link

[WIP] ReinforcementLearning.jl integration #9

Open rejuvyesh opened 2 years ago

rejuvyesh commented 2 years ago

I realized that CommonRLInterface.jl never settled on what to do with continuous action spaces, so directly integrating with RLBase from ReinforcementLearning.jl.

Will add tests and examples with PPO and DDPG.

codecov-commenter commented 2 years ago

Codecov Report

Merging #9 (eb379f6) into main (f9b2fd1) will decrease coverage by 0.09%. The diff coverage is n/a.

Impacted file tree graph

@@            Coverage Diff             @@
##             main       #9      +/-   ##
==========================================
- Coverage   92.41%   92.31%   -0.10%     
==========================================
  Files          81       81              
  Lines        3823     3761      -62     
==========================================
- Hits         3533     3472      -61     
+ Misses        290      289       -1
Impacted Files Coverage Δ
src/Dojo.jl 100.00% <ø> (ø)
src/orientation/quaternion.jl 82.92% <0.00%> (-5.41%) :arrow_down:
src/orientation/mapping.jl 36.36% <0.00%> (-5.31%) :arrow_down:
src/contacts/utilities.jl 40.00% <0.00%> (-2.86%) :arrow_down:
src/joints/rotational/input.jl 42.10% <0.00%> (-1.49%) :arrow_down:
src/joints/joint.jl 88.88% <0.00%> (-0.51%) :arrow_down:
src/contacts/impact.jl 86.20% <0.00%> (-0.46%) :arrow_down:
src/bodies/set.jl 94.54% <0.00%> (-0.37%) :arrow_down:
src/joints/rotational/springs.jl 97.29% <0.00%> (-0.14%) :arrow_down:
src/utilities/methods.jl 96.66% <0.00%> (-0.11%) :arrow_down:
... and 17 more

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 5563639...eb379f6. Read the comment docs.

janbruedigam commented 1 year ago

We should probably rethink the interface to ReinforcementLearning.jl once their updates are done (https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/issues/614)